Revista Mexicana de Ingenieria Biomedica

Fast Computational Modeling Based on the Boundary Element Method Towards the Design of an Ultrasonic Biomedical Applicator

Raquel Martínez-Valdez — 2025-01-01

The aim of this work is to analyze the usage of the boundary element method (BEM) as a fast computational tool for solving large ultrasonic field problems, i.e. 3D models. A proposed tridimensional radiating surface S_R was modeled by means of BEM and the finite element method (FEM). Four time-harmonics models were developed: two containing the entire S_R and two considering a symmetrical plane at half-length of the radiator. BEM solutions were validated with FEM models by contours at -3 dB and -6 dB pressure decays, areas within the contours, elliptical shape ratio E_r and ellipsoidal focal volume approximations. The average differences in pressure and distance at the focus were 39.875 Pa and 0.4515 mm, respectively; the areas within the contours show differences between 0.6 mm² and 2.3 mm². The E_r of the focal zone was over 92 %, while the ellipsoidal volume approximation showed differences between 0.0817 mm³ to 1.4632 mm³ at -3 dB, and 1.2354 mm³ to 4.1144 mm³at -6 dB. Analyzed data suggest the use of BEM to model the ultrasonic beam pattern in a lossless medium during ultrasonic biomedical applicators design, reducing the solution time from 22 h with FEM to 2 min with BEM.

Evaluation of Blood Sample Collection Tubes Using Deep Learning

Ignacio Franco-Alucano — 2025-01-31

Phlebotomy is a procedure to obtain blood samples, mainly for laboratory clinical analysis. The amount of blood, tube identification, and the use of the appropriate tube are characteristics that the health professional visually inspects. Being a manual activity, the possibility of error is latent and can affect quality, workflow, and efficiency. Despite the advancement of industry 4.0 technologies, including artificial intelligence (AI), there is little evidence of applications in clinical laboratories. This study aims to evaluate the suitability of using deep learning (DL) in inspecting tubes with blood samples. Specifically, three architectures, YOLOv5, YOLOv7, and YOLOv8, are tested to detect six classes, including cap color and the presence of labels. The highest precision performance was presented by the YOLOv8 model, obtaining a precision of 0.927 in detection, which shows a high capacity to inspect important characteristics in the phlebotomy service. Therefore, being DL is a suitable alternative to assist health professionals in inspection activities. Future work includes expanding the number of images in a balanced manner.

Synthetic Data Generation for Pediatric Diabetes Research Using GANs and WGANs

Antonio García-Domínguez — 2025-02-07

Pediatric diabetes research is often constrained by data scarcity, hindering the development of accurate predictive models for clinical applications. This study addresses this limitation by evaluating the effectiveness of Generative Adversarial Networks (GANs) and Wasserstein GANs (WGANs) in generating synthetic datasets that replicate the statistical properties of real pediatric diabetes data. A structured methodology was applied, incorporating preprocessing, model design, and dual evaluation metrics: Jensen-Shannon and Kullback-Leibler divergences for statistical fidelity, and a classification model to assess practical utility. Results demonstrate that both models produce high-fidelity synthetic datasets, with WGANs showing superior performance in capturing complex patterns due to improved training stability. Nonetheless, challenges remain in replicating the inherent variability of pediatric data, influenced by growth and developmental factors. This work highlights the potential of synthetic data to augment pediatric diabetes datasets, facilitating the development of robust and generalizable predictive models. Limitations include the dependency on initial data quality and the specificity of the models to pediatric datasets. By addressing critical gaps in data availability, this study contributes to advancing AI-driven healthcare solutions in pediatric diabetes research.